paper-with-me

Papers

Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents

2025-10-06 · Zhiping Zhang, Yi Evie Zhang, Freda Shi, Tianshi Li arxiv

LLM agents require personal information for personalization in order to effectively act on users' behalf, but this raises privacy concerns that can discourage data sharing, limiting both the autonomy levels at which agents can operate and the effectiveness of personalization. Yet the expanded design space of agent autonomy also presents opportunities to shape these effects, which remain underexplored. We conducted a $3\times3$ between-subjects experiment ($N=450$) to study how agent autonomy level influences personalization's effects on users' privacy concerns, trust, and willingness to use, as well as the underlying psychological processes. We find that risk-contingent autonomy, where the agent delegates control to users upon detecting potential privacy leakage, through improving users' perceived control, attenuates personalization's adverse effects by reducing the increase in privacy concerns and the decrease in trust. Our results suggest that designing $\textbf{agent's autonomy}$ that supports $\textbf{human autonomy}$ (both in terms of perceived control and oversight effectiveness) helps users benefit from personalization without being deterred by growing privacy concerns, contributing to the development of trustworthy LLM agents.

📄 PDF Abstract BibTeX arXiv:2510.04465

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Evaluation of Multilingual LLMs Personalized Text Generation Capabilities Targeting Groups and Social-Media Platforms

2026-01-07 · Dominik Macko arxiv

Capabilities of large language models to generate multilingual coherent text have continuously enhanced in recent years, which opens concerns about their potential misuse. Previous research has shown that they can be mis…

Text Generation

A Parameter Privacy-Preserving Strategy for Mixed-Autonomy Platoon Control

2024-01-28 · Jingyuan Zhou, Kaidi Yang

It has been demonstrated that leading cruise control (LCC) can improve the operation of mixed-autonomy platoons by allowing connected and automated vehicles (CAVs) to make longitudinal control decisions based on the info…

Privacy Preserving

GOD model: Privacy Preserved AI School for Personal Assistant

2025-02-24 · PIN AI Team, Bill Sun, Gavin Guo, Regan Peng 외

Personal AI assistants (e.g., Apple Intelligence, Meta AI) offer proactive recommendations that simplify everyday tasks, but their reliance on sensitive user data raises concerns about privacy and trust. To address these…

Imitation LearningPrivacy Preserving

Privacy Protection Against Personalized Text-to-Image Synthesis via Cross-image Consistency Constraints

2025-04-17 · Guanyu Wang, Kailong Wang, Yihao Huang, Mingyi Zhou 외

The rapid advancement of diffusion models and personalization techniques has made it possible to recreate individual portraits from just a few publicly available images. While such capabilities empower various creative a…

Image Generation

Federated Short-Term Load Forecasting with Personalization Layers for Heterogeneous Clients

2023-09-22 · Shourya Bose, Kibaek Kim

The advent of smart meters has enabled pervasive collection of energy consumption data for training short-term load forecasting (STLF) models. In response to privacy concerns, federated learning (FL) has been proposed as…

Federated LearningLoad ForecastingPrivacy Preserving